-
想要加载最优的模型文件而不是最后一个epoch的模型文件，ModelCheckpoint在这里不起作用
我在class ClassificationModel(BaseModel)里面，加了个函数：
```python
def load_weights(self, model_path):
return self.model.load_weights(model_pat…
-
What are the modifications needed to be able to implement LSTM as an example ?
rmmal updated
5 years ago
-
小白一枚，训练完以后效果不是很理想，有没有什么可配置化的参数来提高准确性呢
-
Hi, I'm having an issue installing madmom. Here's the output:
```
pip3 list
Package Version
------------ ---------
aubio 0.4.6
audioread 2.1.6
beatport 0.0.1
certifi …
-
## val_acc计算错误
## 测试代码用《NLP - 基于 BERT 的中文命名实体识别（NER)》文中例子
from kashgari.corpus import *
train_x, train_y = ChinaPeoplesDailyNerCorpus.get_sequence_tagging_data('train')
validate_x, v…
-
I installed Tensoflow from source. I can't restore previous models saved with precompiled Tensorflow (installed via pip). I get lots of these:
```
Caused by op u'save/RestoreV2_56', defined at:
…
-
Hi, TianZhi,
I am trying to implement the training phase of CTPN with TensorFlow based on your code and faster-rcnn. However, I don't quietly understand the meaning of side-refinement or offset regre…
-
Hi,
First of all thanks for sharing your work.
There are some files missing which are UltraProcess.py and letters.txt.
I found that UltraProcess.py is nothing but the preprocess.py in src folde…
-
Regardless of my input len, and only when running predict, not eval, the output argmax will only return 9 labels.
It changes for each input sentence, but it will only return a maximum of 9 predict…
-
Can FastText be used for a multi-label scenario?
Are you planning on implementing the functionality that would basically use all the labels of each document? For now the workaround would be to man…